Genomics-guided Representation Learning for Pathologic Pan-cancer Tumor Microenvironment Subtype Prediction

TL;DR

This paper introduces PathoTME, a genomics-guided Siamese network that improves pan-cancer tumor microenvironment subtype prediction from Whole Slide Images by leveraging genomic data and domain adaptation techniques.

Contribution

The study presents a novel genomics-guided Siamese learning framework with domain adversarial training for accurate TME subtype classification across multiple cancer types.

Findings

Outperforms state-of-the-art methods on TCGA dataset across 23 cancer types.

Effectively leverages genomic information to regularize WSI embeddings.

Reduces tissue type variation impact using Domain Adversarial Neural Network.

Abstract

The characterization of Tumor MicroEnvironment (TME) is challenging due to its complexity and heterogeneity. Relatively consistent TME characteristics embedded within highly specific tissue features, render them difficult to predict. The capability to accurately classify TME subtypes is of critical significance for clinical tumor diagnosis and precision medicine. Based on the observation that tumors with different origins share similar microenvironment patterns, we propose PathoTME, a genomics-guided Siamese representation learning framework employing Whole Slide Image (WSI) for pan-cancer TME subtypes prediction. Specifically, we utilize Siamese network to leverage genomic information as a regularization factor to assist WSI embeddings learning during the training phase. Additionally, we employ Domain Adversarial Neural Network (DANN) to mitigate the impact of tissue type variations. To eliminate domain bias, a dynamic WSI prompt is designed to further unleash the model's capabilities. Our model achieves better performance than other state-of-the-art methods across 23 cancer types on TCGA dataset. Our code is available at https://github.com/Mengflz/PathoTME.